From 54b8027a92acacfe26ab1784b1a254b4cd4fe845 Mon Sep 17 00:00:00 2001
From: aliarifki <aliarifki@outlook.fr>
Date: Fri, 26 May 2023 16:17:32 +0200
Subject: [PATCH] Ajout des derniers process
---
src/bolero.nf | 50 ++++++++++++++-----
src/nf_modules/junction_nanosplicer/main.nf | 11 ++--
src/nf_modules/ont-guppy/{main.fr => main.nf} | 0
src/nf_modules/rna_count/main.nf | 5 +-
src/nf_modules/start_positions/main.nf | 8 +--
5 files changed, 51 insertions(+), 23 deletions(-)
rename src/nf_modules/ont-guppy/{main.fr => main.nf} (100%)
diff --git a/src/bolero.nf b/src/bolero.nf
index f0e8cc3..41e7bda 100755
--- a/src/bolero.nf
+++ b/src/bolero.nf
@@ -1,6 +1,7 @@
#!/usr/bin/env nextflow
nextflow.enable.dsl=2
+//syntax extension DSL2
/*
========================================================================================================================
@@ -73,7 +74,7 @@ if (params.help || params.h) {
****************************************************************
*/
-/* params in */
+/* Params in */
params.skipBC = true
params.gpu_mode = false
@@ -100,6 +101,8 @@ params.seqkit_grep_out = "03_fastq/"
params.cutadapt_out = "04_cutadapt/"
params.minimap2_genome_out = "05_minimap2/"
params.start_position_counts_out = "06_start_positions/"
+params.nanosplicer_out = "07_nanosplicer/"
+params.rna_count_out = "08_RNA_count/"
params.pycoQC_out = "pycoQC/"
/*
@@ -108,6 +111,7 @@ params.pycoQC_out = "pycoQC/"
****************************************************************
*/
+//to print multiline informations
log.info "fast5/q folder : ${params.input}"
log.info "5'RACE adapter sequence : ${params.adapt}"
if(!params.skipBC) log.info "Guppy basecalling calculation using GPU mode : ${params.gpu_mode}."
@@ -161,13 +165,21 @@ if(!params.skipBC) {
// Replace concatenate by seqkit fct to parallelization:
// include { concatenate } from "./nf_modules/seqkit/main.nf"
include { concatenate } from "./nf_modules/concatenate/main.nf"
-
include { cut_5pRACE } from "./nf_modules/cutadapt/main.nf"
include { hbv_genome } from "./nf_modules/minimap2/main.nf"
include { seqkit_grep } from "./nf_modules/seqkit/main.nf"
-include { sort_bam as sort_bam_genome } from './nf_modules/samtools/main.nf' addParams(sort_bam_out: params.minimap2_genome_out)
-include { index_bam as index_bam_genome } from './nf_modules/samtools/main.nf' addParams(index_bam_out: params.minimap2_genome_out)
+include { sort_bam } from './nf_modules/samtools/main.nf' addParams(sort_bam_out: params.minimap2_genome_out)
+include { index_bam } from './nf_modules/samtools/main.nf' addParams(index_bam_out: params.minimap2_genome_out)
+include { sort_index_bam } from './nf_modules/samtools/main.nf' addParams(indexed_bam_out: params.minimap2_genome_out)
include { start_position_counts } from "./nf_modules/samtools/main.nf"
+include { start_position_individuals } from "./nf_modules/start_positions/main.nf"
+include { jwr_checker } from "./nf_modules/nanosplicer/main.nf"
+include { junctions_nanosplicer } from "./nf_modules/junction_nanosplicer/main.nf"
+include { rna_count } from "./nf_modules/rna_count/main.nf"
+
+/////////////////////////////////////////////////////////
+// script R avec classification des reads par type d'ARN et graphiques associés
+
// creation des fonctions NanoSplicer:
// include { jwr_check } from "./nf_modules/nanosplicer/main.nf"
@@ -200,19 +212,33 @@ workflow {
}
//####################### PREPROCESSING #######################
- /*
+
+
+ //Filtration (seqkit_grep looks for the 5'RACE and the gsp patterns in the reads to keep only mature ARNs)
seqkit_grep(concatenate.out.merged_fastq, params.adapt, params.gsp)
+
+ //Cut of the 5'RACE sequence
cut_5pRACE(seqkit_grep.out.filtered_fastq, params.adapt)
//########################## MAPPING ##########################
-
+
+
hbv_genome(cut_5pRACE.out.fastq_cutadapt, genome)
- sort_bam_genome(hbv_genome.out.bam)
- index_bam_genome(sort_bam_genome.out.sorted_bam.collect())
+ sort_index_bam(hbv_genome.out.bam)
+ // index_bam(sort_bam_genome.out.sorted_bam.collect())
- //###################### QUANTIFICATION #######################
+ //###################### START POSITIONS #######################
- start_position_counts(sort_bam_genome.out.sorted_bam)
- */
+ start_position_counts(sort_index_bam.out.indexed_bam)
+ start_position_individuals(start_position_counts.out.count)
-}
\ No newline at end of file
+ //#################### VARIANTS D'EPISSAGE ####################
+
+ jwr_checker(sort_index_bam.out.indexed_bam)
+ junctions_nanosplicer(start_position_individuals.out.classification_of_reads, jwr_checker.out.nanosplicer_jwr)
+
+ //#################### VARIANTS D'EPISSAGE ####################
+
+ rna_count(junctions_nanosplicer.out.identified_SPvariants, start_position_individuals.out.classification_of_reads)
+
+}
diff --git a/src/nf_modules/junction_nanosplicer/main.nf b/src/nf_modules/junction_nanosplicer/main.nf
index 4af81e2..9000bc8 100644
--- a/src/nf_modules/junction_nanosplicer/main.nf
+++ b/src/nf_modules/junction_nanosplicer/main.nf
@@ -1,13 +1,13 @@
version = "1.0"
-container_url = "xgrand/r-scripts:${version}"
+container_url = "xgrand/r-bolero:${version}"
-params.junctions_out = ""
+params.nanosplicer_out = ""
process junctions_nanosplicer{
container = "${container_url}"
label "small_mem_mono_cpus"
tag "identification de variants d'épissage"
- if (params.junctions_out != "") {
- publishDir "results/${params.junctions_out}", mode: 'copy'
+ if (params.nanosplicer_out != "") {
+ publishDir "results/${params.nanosplicer_out}", mode: 'copy'
}
input:
@@ -17,10 +17,11 @@ process junctions_nanosplicer{
output:
path("Rplots.pdf")
path("JWR_check_parsed.csv")
+ path("*.jpg")
path("identified_SPvariants.csv"), emit: identified_SPvariants
script:
"""
- Rscript Junctions_NanoSplicer.R -c txt -j csv
+ Rscript /Junctions_NanoSplicer.R -c ${txt} -j ${csv}
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/ont-guppy/main.fr b/src/nf_modules/ont-guppy/main.nf
similarity index 100%
rename from src/nf_modules/ont-guppy/main.fr
rename to src/nf_modules/ont-guppy/main.nf
diff --git a/src/nf_modules/rna_count/main.nf b/src/nf_modules/rna_count/main.nf
index 5899f2e..4d9b6f4 100644
--- a/src/nf_modules/rna_count/main.nf
+++ b/src/nf_modules/rna_count/main.nf
@@ -1,5 +1,5 @@
version = "1.0"
-container_url = "xgrand/r-scripts:${version}"
+container_url = "xgrand/r-bolero:${version}"
params.rna_count_out = ""
process rna_count{
@@ -17,9 +17,10 @@ process rna_count{
output:
path("*.csv")
path("*.pdf")
+ path("*.jpg")
script:
"""
- Rscript HBV_RNAs_count.R -s spvariants -c classification
+ Rscript /HBV_RNAs_count.R -s ${spvariants} -c ${classification}
"""
}
diff --git a/src/nf_modules/start_positions/main.nf b/src/nf_modules/start_positions/main.nf
index 4a29e9f..4b97e0c 100644
--- a/src/nf_modules/start_positions/main.nf
+++ b/src/nf_modules/start_positions/main.nf
@@ -1,7 +1,7 @@
version = "1.0"
-container_url = "xgrand/r-scripts:${version}"
+container_url = "xgrand/r-bolero:${version}"
-params.start_position_counts_out = ""
+params.start_position_counts_out =""
process start_position_individuals{
container = "${container_url}"
label "small_mem_mono_cpus"
@@ -9,17 +9,17 @@ process start_position_individuals{
if (params.start_position_counts_out != "") {
publishDir "results/${params.start_position_counts_out}", mode: 'copy'
}
-
input:
path(start_position_counts)
output:
path("Rplots.pdf")
+ path("*.jpg")
path("Count_reads_per_promoter.tsv")
path("classification_of_reads_per_RNA.txt"), emit: classification_of_reads
script:
"""
- Rscript start_positions.R -i start_position_counts
+ Rscript /Start_positions.R -i ${start_position_counts}
"""
}
\ No newline at end of file
--
GitLab